Buscar
Mostrando ítems 21-30 de 50
Reconhecimento de caracteres manuscritos off-line utilizando Support Vector Machine (SVM)
(Universidade Tecnológica Federal do ParanáPonta GrossaBrasilDepartamento Acadêmico de InformáticaTecnologia em Análise e Desenvolvimento de SistemasUTFPR, 2019-11-07)
This work investigates the use of Support Vector Machine (SVM's) for recognition of uppercase handwritten characters of the Latin alphabet. The experiment made use of offline data from IRONOFF database. The data had already ...
A New Artificial Immune System Based on Continuous Learning for Pattern Recognition
(Instituto de Informática - Universidade Federal do Rio Grande do Sul, 2020)
A new artificial immune system based on continuous learning for pattern recognitionUm novo sistema imunológico artificial baseado no aprendizado contínuo para reconhecimento de padrões
(2020-01-01)
This paper presents a novel approach for pattern recognition based on continuous training inspired by the biological immune system operation. The main objective of this paper is to present a method capable of continually ...
Simulação de forças físicas para segmentação e restauração de dígitos e sequências de dígitos em imagens de documentos manuscritos
(Universidade Federal de PernambucoUFPEBrasilPrograma de Pos Graduacao em Ciencia da Computacao, 2016)
Reconhecimento de estilos de escrita em documentos manuscritos: uma abordagem em nível de documentos, linhas e palavras
(Universidade Tecnológica Federal do ParanáCampo MouraoBrasilDepartamento Acadêmico de ComputaçãoCiência da ComputaçãoUTFPR, 2019-11-28)
Script recognition is a necessary step in automating the recognition of Optical Character Recognition (OCR) systems. The task of script recognition in handwritten documents is challenging due to the similarity between some ...
Minimization of the line resistance impact on memdiode-based simulations of multilayer perceptron arrays applied to pattern recognition
(MDPI AG, 2021-03)
In this paper, we extend the application of the Quasi-Static Memdiode model to the real-istic SPICE simulation of memristor-based single (SLPs) and multilayer perceptrons (MLPs) in-tended for large dataset pattern recognition. ...
Reconhecimento óptico de caracteres manuscritos usando redes neurais convolucionais
(Universidade Estadual Paulista (Unesp), 2018-11-14)
The human being by nature has a great capacity to recognize visual patterns with varying degrees of complexity - we are able to identify shapes, lines, curves, etc - and thus differentiating letters and digits from each ...